Matches in SemOpenAlex for { <https://semopenalex.org/work/W2178726985> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2178726985 abstract "This paper proposes a new online feature extraction method called Incremental Recursive Fisher Linear Discriminant (IRFLD) whose batch learning algorithm called RFLD has been proposed by Xiang et al. In the conventional Linear Discriminant Analysis (LDA), the number of discriminant vectors is limited to the number of classes minus one due to the rank of the between-class covariance matrix. However, RFLD and the proposed IRFLD can break this limit; that is, an arbitrary number of discriminant vectors can be obtained. In the proposed IRFLD, the Pang et al.'s Incremental Linear Discriminant Analysis (ILDA) is extended such that effective discriminant vectors are recursively searched for the complementary space of a conventional discriminant subspace. In addition, to estimate a suitable number of effective discriminant vectors, the classification accuracy is evaluated with a cross-validation method in an online manner. For this purpose, validation data are obtained by performing the k-means clustering against incoming training data and previous validation data. The performance of IRFLD is evaluated for 16 benchmark data sets. The experimental results show that the final classification accuracies of IRFLD are always better than those of ILDA. We also reveal that this performance improvement is attained by adding discriminant vectors in a complementary LDA subspace." @default.
- W2178726985 created "2016-06-24" @default.
- W2178726985 creator A5048669520 @default.
- W2178726985 creator A5048703263 @default.
- W2178726985 date "2011-01-01" @default.
- W2178726985 modified "2023-09-26" @default.
- W2178726985 title "An Improvement of Incremental Recursive Fisher Linear Discriminant for Online Feature Extraction" @default.
- W2178726985 cites W1520101322 @default.
- W2178726985 cites W1970748944 @default.
- W2178726985 cites W1971747485 @default.
- W2178726985 cites W2020717119 @default.
- W2178726985 cites W2041657594 @default.
- W2178726985 cites W2059998433 @default.
- W2178726985 cites W2078216288 @default.
- W2178726985 cites W2097179345 @default.
- W2178726985 cites W2105628133 @default.
- W2178726985 cites W2117388026 @default.
- W2178726985 cites W2121085248 @default.
- W2178726985 cites W2129476886 @default.
- W2178726985 cites W2135346934 @default.
- W2178726985 cites W2140136381 @default.
- W2178726985 cites W2141681031 @default.
- W2178726985 cites W2164552042 @default.
- W2178726985 cites W3099514962 @default.
- W2178726985 cites W3119651796 @default.
- W2178726985 cites W3022026283 @default.
- W2178726985 doi "https://doi.org/10.1541/ieejeiss.131.1368" @default.
- W2178726985 hasPublicationYear "2011" @default.
- W2178726985 type Work @default.
- W2178726985 sameAs 2178726985 @default.
- W2178726985 citedByCount "0" @default.
- W2178726985 crossrefType "journal-article" @default.
- W2178726985 hasAuthorship W2178726985A5048669520 @default.
- W2178726985 hasAuthorship W2178726985A5048703263 @default.
- W2178726985 hasConcept C104500394 @default.
- W2178726985 hasConcept C11413529 @default.
- W2178726985 hasConcept C153180895 @default.
- W2178726985 hasConcept C154945302 @default.
- W2178726985 hasConcept C181367576 @default.
- W2178726985 hasConcept C185142706 @default.
- W2178726985 hasConcept C31510193 @default.
- W2178726985 hasConcept C32834561 @default.
- W2178726985 hasConcept C33923547 @default.
- W2178726985 hasConcept C41008148 @default.
- W2178726985 hasConcept C58596280 @default.
- W2178726985 hasConcept C69738355 @default.
- W2178726985 hasConcept C73555534 @default.
- W2178726985 hasConcept C78397625 @default.
- W2178726985 hasConcept C83665646 @default.
- W2178726985 hasConceptScore W2178726985C104500394 @default.
- W2178726985 hasConceptScore W2178726985C11413529 @default.
- W2178726985 hasConceptScore W2178726985C153180895 @default.
- W2178726985 hasConceptScore W2178726985C154945302 @default.
- W2178726985 hasConceptScore W2178726985C181367576 @default.
- W2178726985 hasConceptScore W2178726985C185142706 @default.
- W2178726985 hasConceptScore W2178726985C31510193 @default.
- W2178726985 hasConceptScore W2178726985C32834561 @default.
- W2178726985 hasConceptScore W2178726985C33923547 @default.
- W2178726985 hasConceptScore W2178726985C41008148 @default.
- W2178726985 hasConceptScore W2178726985C58596280 @default.
- W2178726985 hasConceptScore W2178726985C69738355 @default.
- W2178726985 hasConceptScore W2178726985C73555534 @default.
- W2178726985 hasConceptScore W2178726985C78397625 @default.
- W2178726985 hasConceptScore W2178726985C83665646 @default.
- W2178726985 hasLocation W21787269851 @default.
- W2178726985 hasOpenAccess W2178726985 @default.
- W2178726985 hasPrimaryLocation W21787269851 @default.
- W2178726985 hasRelatedWork W199919684 @default.
- W2178726985 hasRelatedWork W2003924941 @default.
- W2178726985 hasRelatedWork W2021920484 @default.
- W2178726985 hasRelatedWork W2037183730 @default.
- W2178726985 hasRelatedWork W2057055871 @default.
- W2178726985 hasRelatedWork W2082638360 @default.
- W2178726985 hasRelatedWork W2094592018 @default.
- W2178726985 hasRelatedWork W2105081321 @default.
- W2178726985 hasRelatedWork W2109101449 @default.
- W2178726985 hasRelatedWork W2109612424 @default.
- W2178726985 hasRelatedWork W2113812158 @default.
- W2178726985 hasRelatedWork W2118709588 @default.
- W2178726985 hasRelatedWork W2154919220 @default.
- W2178726985 hasRelatedWork W2184084457 @default.
- W2178726985 hasRelatedWork W2350268869 @default.
- W2178726985 hasRelatedWork W2374730777 @default.
- W2178726985 hasRelatedWork W2386228546 @default.
- W2178726985 hasRelatedWork W2489198074 @default.
- W2178726985 hasRelatedWork W2788358253 @default.
- W2178726985 hasRelatedWork W798006966 @default.
- W2178726985 isParatext "false" @default.
- W2178726985 isRetracted "false" @default.
- W2178726985 magId "2178726985" @default.
- W2178726985 workType "article" @default.